End of training

README.md

@@ -0,0 +1,66 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: liuhaotian/llava-v1.5-13b
+model-index:
+- name: llava_13b_exact_gps_coordinates
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# llava_13b_exact_gps_coordinates
+
+This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b](https://huggingface.co/liuhaotian/llava-v1.5-13b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4478
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.8774        | 1.0   | 9    | 1.0233          |
+| 0.2187        | 2.0   | 18   | 1.1222          |
+| 0.0704        | 3.0   | 27   | 1.1833          |
+| 0.0295        | 4.0   | 36   | 1.3706          |
+| 0.0129        | 5.0   | 45   | 1.4478          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.37.2
+- Pytorch 2.1.2+cu121
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def47d5792bd685abde9cf79bb54db8ab2dc0ede932f1edee158f850bf69cc4c
+size 1001466944

config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 2e-05,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "llava_llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": [
+      "mm_projector"
+    ],
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68ddfe6ce0358ed97665d43ab246ef5884bd28da1ad884819ce894242a22ee8
+size 62937264

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,340 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 45,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0,
+      "loss": 1.8683,
+      "step": 1
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002,
+      "loss": 1.3275,
+      "step": 2
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002,
+      "loss": 1.4462,
+      "step": 3
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002,
+      "loss": 1.2039,
+      "step": 4
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002,
+      "loss": 1.1195,
+      "step": 5
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 1.0235,
+      "step": 6
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002,
+      "loss": 0.977,
+      "step": 7
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002,
+      "loss": 0.8402,
+      "step": 8
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0002,
+      "loss": 0.8774,
+      "step": 9
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.023256778717041,
+      "eval_runtime": 5.1515,
+      "eval_samples_per_second": 9.706,
+      "eval_steps_per_second": 0.388,
+      "step": 9
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0002,
+      "loss": 0.663,
+      "step": 10
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0002,
+      "loss": 0.4821,
+      "step": 11
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002,
+      "loss": 0.4614,
+      "step": 12
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0002,
+      "loss": 0.5169,
+      "step": 13
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0002,
+      "loss": 0.4671,
+      "step": 14
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0002,
+      "loss": 0.4509,
+      "step": 15
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.0002,
+      "loss": 0.3006,
+      "step": 16
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.0002,
+      "loss": 0.2702,
+      "step": 17
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002,
+      "loss": 0.2187,
+      "step": 18
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1222225427627563,
+      "eval_runtime": 5.1565,
+      "eval_samples_per_second": 9.696,
+      "eval_steps_per_second": 0.388,
+      "step": 18
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.0002,
+      "loss": 0.1543,
+      "step": 19
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.0002,
+      "loss": 0.105,
+      "step": 20
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 0.0002,
+      "loss": 0.0996,
+      "step": 21
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 0.0002,
+      "loss": 0.1239,
+      "step": 22
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 0.0002,
+      "loss": 0.0898,
+      "step": 23
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0002,
+      "loss": 0.0557,
+      "step": 24
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 0.0002,
+      "loss": 0.0948,
+      "step": 25
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 0.0002,
+      "loss": 0.098,
+      "step": 26
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0704,
+      "step": 27
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.183333396911621,
+      "eval_runtime": 5.3107,
+      "eval_samples_per_second": 9.415,
+      "eval_steps_per_second": 0.377,
+      "step": 27
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 0.0002,
+      "loss": 0.0357,
+      "step": 28
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 0.0002,
+      "loss": 0.0341,
+      "step": 29
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 0.0002,
+      "loss": 0.0406,
+      "step": 30
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 0.0002,
+      "loss": 0.0258,
+      "step": 31
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 0.0002,
+      "loss": 0.0342,
+      "step": 32
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 0.0002,
+      "loss": 0.0333,
+      "step": 33
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 0.0002,
+      "loss": 0.0317,
+      "step": 34
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 0.0002,
+      "loss": 0.04,
+      "step": 35
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0295,
+      "step": 36
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.370598554611206,
+      "eval_runtime": 5.2178,
+      "eval_samples_per_second": 9.582,
+      "eval_steps_per_second": 0.383,
+      "step": 36
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 0.0002,
+      "loss": 0.0114,
+      "step": 37
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 0.0002,
+      "loss": 0.0181,
+      "step": 38
+    },
+    {
+      "epoch": 4.33,
+      "learning_rate": 0.0002,
+      "loss": 0.0141,
+      "step": 39
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 0.0002,
+      "loss": 0.0099,
+      "step": 40
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 0.0002,
+      "loss": 0.0085,
+      "step": 41
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 0.0002,
+      "loss": 0.0155,
+      "step": 42
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 0.0002,
+      "loss": 0.0279,
+      "step": 43
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 0.0002,
+      "loss": 0.0094,
+      "step": 44
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0129,
+      "step": 45
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.4478448629379272,
+      "eval_runtime": 5.1693,
+      "eval_samples_per_second": 9.672,
+      "eval_steps_per_second": 0.387,
+      "step": 45
+    },
+    {
+      "epoch": 5.0,
+      "step": 45,
+      "total_flos": 8.470619890489754e+16,
+      "train_loss": 0.3519688956853416,
+      "train_runtime": 299.0301,
+      "train_samples_per_second": 4.732,
+      "train_steps_per_second": 0.15
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 45,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 50000,
+  "total_flos": 8.470619890489754e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04017acfc6572bbb6f73cd57c151dbe662da3035ce47f0728fbc675b33a53af9
+size 6840